Your Location：
Home >
Browse articles >
An anti-collision algorithm for robotic search-and-rescue tasks in unknown dynamic environments
Regular Papers | Updated：2024-04-29

    • An anti-collision algorithm for robotic search-and-rescue tasks in unknown dynamic environments

    • 面向未知动态环境的机器人搜救任务避障算法
    • “针对移动机器人在未知动态环境中执行多目标搜索救援任务的问题，研究团队提出了一种基于混合策略纳什均衡的Dyna-Q（MNDQ）算法。该算法通过引入多目标分层结构，简化了多目标的表示，降低了计算复杂性。同时，提出了基于动态风险相对位置的风险监控机制，帮助机器人有效规避潜在碰撞和不必要的绕行。为提高采样效率，研究团队将Dyna-Q与混合策略纳什均衡相结合，形成了MNDQ算法。该算法使机器人在决策时采用概率形式，最大化预期回报，提升了Dyna-Q算法的整体性能。通过一系列模拟实验验证，MNDQ表现出色，展现了其鲁棒性，为未来自主机器人导航任务提供了有力解决方案。这项研究不仅丰富了移动机器人领域的理论体系，还为复杂环境下的机器人导航提供了新的思路和方法。随着技术的不断进步，相信MNDQ算法将在更多实际应用场景中展现其潜力。”
    • Frontiers of Information Technology & Electronic Engineering   Vol. 25, Issue 4, Pages: 569-584(2024)

    • DOI：10.1631/FITEE.2300151    

      CLC： TP183

    • Received：03 March 2023，

      Accepted：25 August 2023，

      Published：0 April 2024

    Scan QR Code

  • Yang CHEN, Dianxi SHI, Huanhuan YANG, et al. An anti-collision algorithm for robotic search-and-rescue tasks in unknown dynamic environments[J]. Frontiers of Information Technology & Electronic Engineering, 2024, 25(4): 569-584. DOI： 10.1631/FITEE.2300151.

  •  
  •  

0

Views

132

Downloads

0

CSCD

PlumX

>
Alert me when the article has been cited
Submit
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

Decentralized multi-agent reinforcement learning with networked agents: recent advances
Jiu fusion artificial intelligence (JFA): a two-stage reinforcement learning model with hierarchical neural networks and human knowledge for Tibetan Jiu chess
Efficient learning of robust multigait quadruped locomotion for minimizing the cost of transport
Reinforcement learning based privacy-preserving consensus tracking control of nonstrict-feedback discrete-time multi-agent systems
Domain adaptation in reinforcement learning: a comprehensive and systematic study

Related Author

Kaiqing ZHANG
Zhuoran YANG
Tamer BAŞAR
Xiali LI
Xiaoyu FAN
Junzhi YU
Xianmu CAIRANG
Ping LAN

Related Institution

Department of Operations Research and Financial Engineering, Princeton University
Coordinated Science Laboratory, University of Illinois at Urbana-Champaign
School of Information Science and Technology, Xizang University
State Key Laboratory of General Artificial Intelligence, Peking University
State Key Laboratory for Turbulence and Complex Systems, Peking University
0